logo

SCIENCE CHINA Information Sciences, Volume 58, Issue 1: 012102(17)-012102(17)(2015) https://doi.org/10.1007/s11432-014-5143-3

Single image haze removal via depth-based contrast stretching transform

More info
  • AcceptedJan 28, 2014
  • PublishedDec 26, 2014

Abstract

Under the weather of haze, fog, or smoke, outdoor images show poor visibility and low contrast. Low contrast results in the difficulty for carrying out basic local feature (e.g., interest points and edges) detection algorithms, which are necessary procedures in some computer vision applications. Hence, increasing contrast of degraded images is very important since it is helpful in finding more distinct features from haze images. However, few single image haze removal methods can simultaneously achieve clear visibility, sufficiently high contrast, and simplicity. In this paper, we propose an intuitive and effective method, called the depth-based contrast stretching transform (DCST), to simultaneously obtain clear visibility and enhance contrast of a single haze gray image. The DCST stretches the contrast of haze images based on the coarse depth layers of scenes. Our method is simple and almost real time and can be extended to color images. We analyze in detail that the image stretched by the DCST has a higher local contrast than the image recovered via the physical-based model. Experiments demonstrate that images stretched by the DCST have excellent visibility and contrast compared with a few existing algorithms. Compelling performance is also presented by comparing the proposed method with other representative methods in the application of local feature detection.


References

[1] Harris C, Stephens M. A combined corner and edge detector. In: Proceedings of 4th Alvey Vision Conference,Manchester, 1988. 147-151. Google Scholar

[2] Sobel I. Camera models and machine perception. Ph.D. thesis. Stanford University, 1970. Google Scholar

[3] Stark J A. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Trans ImageProcess, 2000, 9: 889-896. Google Scholar

[4] Pizer S M, Amburn E P, Austin J D, et al. Adaptive histogram equalization and its variations. Comput Vis GraphImage Process, 1987, 39: 355-368. Google Scholar

[5] Farid H. Blind inverse Gamma correction. IEEE Trans Image Process, 2001, 10: 1428-1433. Google Scholar

[6] Deng G. A generalized unsharp masking algorithm. IEEE Trans Image Process, 2011, 20: 1249-1261. Google Scholar

[7] Zhang Y D, Wu L N, Wang S H, et al. Color image enhancement based on HVS and PCNN. Sci China Inf Sci, 2010,53: 1963-1976. Google Scholar

[8] Li M. A fast algorithm for color image enhancement with total variation regularization. Sci China Inf Sci, 2010, 53:1913-1916. Google Scholar

[9] Narasimhan S G, Nayar S K. Contrast restoration of weather degraded images. IEEE Trans Pattern Anal Mach Intell,2003, 25: 713-724. Google Scholar

[10] Shwartz S, Namer E, Schechner Y Y. Blind haze separation. In: Proceedings of IEEE Conference on Computer Visionand Pattern Recognition, New York, 2006. 1984-1991. Google Scholar

[11] Kopf J, Neubert B, Chen B, et al. Deep photo: model-based photograph enhancement and viewing. ACM TransGraph, 2008, 27: 116. Google Scholar

[12] Oakley J P, Satherley B L. Improving image quality in poor visibility conditions using a physical model for contrastdegradation. IEEE Trans Image Process, 1998, 7: 167-179. Google Scholar

[13] Narasimhan S G, Nayar S K. Interactive (de) weathering of an image using physical models. In: Proceedings of IEEEWorkshop Color and Photometric Methods in Computer Vision, 2009. 1-8. Google Scholar

[14] Schaul L, Fredembach C, Susstrunk S. Color image dehazing using the near-infrared. In: Proceedings of IEEE InternationalConference on Image Processing, Cairo, 2009. 1629-1632. Google Scholar

[15] Fattal R. Single image dehazing. ACM Trans Graph. 2008, 27: 1-9. Google Scholar

[16] Tan R T. Visibility in bad weather from a single image. In: Proceedings of IEEE Conference on Computer Vision andPattern Recognition, Anchorage, 2008. 1-8. Google Scholar

[17] He K M, Sun J, Tang X O. Single image haze removal using dark channel prior. In: Proceedings of IEEE Conferenceon Computer Vision and Pattern Recognition, Miami, 2009. 1956-1963. Google Scholar

[18] Ding M, Tong R F. Efficient dark channel based image dehazing using quadtrees. Sci China Inf Sci, 2013, 56: 092120. Google Scholar

[19] Gibson K, Vo D, Nguyen T. An investigation of dehazing effects on image and video coding. IEEE Trans ImageProcess, 2012, 21: 662-673. Google Scholar

[20] Tarel J P, Hauti`ere N. Fast visibility restoration from a single color or gray level image. In: Proceedings of IEEEInternational Conference on Computer Vision, Kyoto, 2009. 2201-2208. Google Scholar

[21] Nishino K, Kratz L, Lombardi S. Bayesian defogging. Int J Comput Vision, 2012, 98: 263-278. Google Scholar

[22] Deng G. A generalized logarithmic image processing model based on the gigavision sensor model. IEEE Trans ImageProcess, 2012, 21: 1406-1414. Google Scholar

[23] Gevrekci M, Gunturk B K. Illumination robust interest point detection. Comput Vis Image Understand, 2009, 113:565-571. Google Scholar

[24] He K M, Sun J, Tang X O. Guided image filtering. In: Proceedings of European Conference on Computer Vision,Heraklion, 2010. 1-14. Google Scholar

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1